新手求助~（关于初级的神经网络问题）

Continue

各位大虾，我在网上看到的教程里的一个程序段，本来想要试试看的：
8 k3 `8 h: m& \3 F( T4 A" vnet=newff([-1 2; 0 5],[3,1],{'tansig','purelin'},'traingd');
, \0 P6 u$ i( F

1 D% n. S) y8 Z& j, H8 W  cnet.trainParam.show = 50;
3 }- w# a* D! p  F5 Lnet.trainParam.lr = 0.05;
net.trainParam.epochs = 300;
net.trainParam.goal = 1e-5;
p = [-1 -1 2 2;0 5 0 5];
% [- N: j( v( M. f3 Y' X" Vt = [-1 -1 1 1];
5 _4 p$ B$ u/ S' Y- }6 E

net=train(net,p,t);
TRAINGD, Epoch 0/300, MSE 1.59423/1e-05, Gradient 2.76799/1e-10
$ C# Z8 T) k4 m+ X4 \. L

TRAINGD, Epoch 50/300, MSE 0.00236382/1e-05, Gradient 0.0495292/1e-10
7 W+ G4 O3 u) r2 M7 U% ]TRAINGD, Epoch 100/300, MSE 0.000435947/1e-05, Gradient 0.0161202/1e-10
" c5 {, Z% N4 l% R; WTRAINGD, Epoch 150/300, MSE 8.68462e-05/1e-05, Gradient 0.00769588/1e-10
5 n1 o4 _' P7 x6 u* W0 J/ F4 t! m/ \TRAINGD, Epoch 200/300, MSE 1.45042e-05/1e-05, Gradient 0.00325667/1e-10
TRAINGD, Epoch 211/300, MSE 9.64816e-06/1e-05, Gradient 0.00266775/1e-10
' ]5 x8 m; L+ H; J4 s* \, a3 l1 _TRAINGD, Performance goal met.
, w, l) _9 g, q! u# K- na = sim(net,p)
1 {. ]2 g+ e% U' G4 u) q1 j, v
) L2 E/ s/ \- {9 `
plot(p,t,p,a,'o')


5 x( K8 K% ?" ^# s但是为什么老是报错：
& ], h+ c( ~, ?/ Q  g9 a% j??? Input argument "net" is undefined.